SageAttention with StabilityMatrix on Linux
_qattn_sm80.cpython-310-x86_64-linux-gnu.so - Optimized for SM 8.0/8.6 GPUs _qattn_sm89.cpython-310-x86_64-linux-gnu.so - Optimized for SM 8.9 GPUs (your RTX 4090) _fused.cpython-310-x86_64-linux-gnu.so - Fused kernel operations
Comments